We address the problem of segmenting a sequence of images of natural scenes into disjoint regions that are characterized by constant spatio-temporal statistics. We model the spatio-temporal dynamics in each region by Gauss-Markov models, and infer the model parameters as well as the boundary of the regions in a variational optimization framework. Numerical results demonstrate that - in contrast to purely texture-based segmentation schemes - our method is effective in segmenting regions that differ in their dynamics even when spatial statistics are identical.
Dynamic texture segmentation
Proceedings Ninth IEEE International Conference on Computer Vision ; 1236-1242 vol.2
2003-01-01
608505 byte
Conference paper
Electronic Resource
English
British Library Conference Proceedings | 2003
|Quaternion color texture segmentation
British Library Online Contents | 2007
|Dynamic texture segmentation based on deterministic partially self-avoiding walks
British Library Online Contents | 2013
|Image Segmentation by Texture Analysis
British Library Conference Proceedings | 1999
|Nested partitions using texture segmentation
IEEE | 2002
|